Publication
Active Learning for Imbalanced Civil Infrastructure Data
Publications associées (41)
Promoting Computational Thinking Skills in Non-Computer Science Students Gamifying Computational Notebooks to Increase Student Engagement
Denis Gillet, Juan Carlos Farah, Adrian Christian Holzer, Marc Lafuente Martinez, Pascal Felber
Computational thinking (CT) skills are becoming increasingly relevant for future professionals across all domains, beyond computer science (CS). As such, an increasing number of bachelor and masters programs outside of the computer science discipline integ ...
2022Active Learning of Bayesian Probabilistic Movement Primitives
Jean-Marc Odobez, Sylvain Calinon, Hakan Girgin, Thibaut Antoine Kulak
Learning from Demonstration permits non-expert users to easily and intuitively reprogram robots. Among approaches embracing this paradigm, probabilistic movement primitives (ProMPs) are a well-established and widely used method to learn trajectory distribu ...
IEEE2021Informative sample generation using class aware generative adversarial networks for classification of chest Xrays
Training robust deep learning (DL) systems for disease detection from medical images is challenging due to limited images covering different disease types and severity. The problem is especially acute, where there is a severe class imbalance. We propose an ...
2019Learning Approach to Delineation of Curvilinear Structures in 2D and 3D Images
Detection of curvilinear structures has long been of interest due to its wide range of applications. Large amounts of imaging data could be readily used in many fields, but it is practically not possible to analyze them manually. Hence, the need for automa ...
EPFL2019DeepFly3D, a deep learning-based approach for 3D limb and appendage tracking in tethered, adult Drosophila
Pascal Fua, Pavan P Ramdya, Helge Jochen Rhodin, Semih Günel, Daniel Eduardo Morales Garza, João Henrique Campagnolo
Studying how neural circuits orchestrate limbed behaviors requires the precise measurement of the positions of each appendage in 3-dimensional (3D) space. Deep neural networks can estimate 2-dimensional (2D) pose in freely behaving and tethered animals. Ho ...
2019Learning to Reduce Annotation Load
Modern machine learning methods and their applications in computer vision are known to crave for large amounts of training data to reach their full potential. Because training data is mostly obtained through humans who manually label samples, it induces a ...
EPFL2019Flipped classroom in Linear Algebra
Simone Deparis, Roland John Tormey, Cécile Hardebolle
As Saitta et al. report in [1], the flipped classroom model builds on several well-known teaching approaches. In particular, using in-class time for more active learning activities as been constantly shown by research to improve learning [2]. In this prese ...
2019TIP: Tangible e-Ink Paper Manipulatives for Classroom Orchestration
Pierre Dillenbourg, Wafa Monia Benkaouar Johal, Ayberk Özgür, Hala Khodr, Alex The Duy Tran
While digital tools are more and more used in classrooms, teachers' common practice remains to use photocopied paper documents to share and collect learning exercises from their students. With the Tangible e-Ink Paper (TIP) system, we aim to explore the us ...
ACM2019Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network
Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity. We propose an active learning (AL) framework to select most informative samples ...
Springer2018Active Interdisciplinary Learning in a Design Thinking Course: Going to Class for a Reason
Denis Gillet, Marc Laperrouza, Adrian Christian Holzer
New technologies such as MOOCs make it crucial for universities to find the added value of bringing students to campus. Designing lectures that foster more interactions could address this issue, as student engagement and interaction are harder to replicate ...
IEEE2018